Intro
Preface
Organization
Contents
Speech and Natural language Processing
A Critical Insight into Automatic Visual Speech Recognition System
1 Introduction
2 Related Work
3 Applications of Speech Recognition
3.1 In the Workplace
3.2 In Banking
3.3 In Marketing
4 Convolutional Neural Network
5 Kaldi Toolkit
6 Proposed Methodology
6.1 Combining Residual Networks with LSTMs for Lipreading
6.2 Deep Word Embedding
6.3 Lrw-1000
6.4 Marathi Language Vowels and Consonants
7 Features Extraction
7.1 Visual Preprocessing

7.2 Region of Interest (ROI) Extraction
7.3 Visual Feature Extraction
8 Conclusion
References
Speaker Independent Accent Based Speech Recognition for Malayalam Isolated Words: An LSTM-RNN Approach
1 Introduction
2 Related Work
2.1 Accent Based Speech Recognition Using RNN in Literature
3 Proposed Methodology and Design
3.1 The Blueprint of the Model
3.2 Dataset
3.3 Feature Extraction
3.4 Model Building Using LSTMRNN
4 Result and Discussion
5 The Performance Evaluation Metrics
6 Conclusion
References

A Review on Speech Synthesis Based on Machine Learning
1 Introduction
2 Literature Survey
2.1 Support Vector Machine (SVM) Based Speech Enhancement Systems
2.2 Neural Network Based Text to Speech Synthesis Technique
2.3 Multi -level Speech Synthesis Based Gaussian Mixture Modeling
2.4 Speech Synthesis Using Generative Adversarial Network
2.5 DNN Based Speech Synthesis Technique
2.6 Speech Synthesis Techniques Based on HMM
2.7 Multilingual Text to Speech Synthesis
3 Comparative Analysis and Discussion of Speech Synthesis Framework
4 Conclusion
References

Hindi Phoneme Recognition
A Review
1 Introduction
2 Related Work
3 Hindi Language
4 Feature Extraction Methods
5 Classification Methods
6 Results and Analysis
7 Conclusion
References
Comparison of Modelling ASR System with Different Features Extraction Methods Using Sequential Model
1 Introduction
2 Related Work
3 Experiment Conducted
4 Results and Outcomes
5 Conclusion
References
Latest Trends in Deep Learning for Automatic Speech Recognition System
1 Introduction
2 Deep Learning
2.1 Auto-encoder
2.2 Convolutional Neural Network

2.3 Generative Adversarial Network
2.4 Restricted Boltzmann Machine
2.5 Deep Belief Network
2.6 Deep Stacking Network
2.7 Long Short-Term Memory
3 Related Work
4 Comparison Table
5 Characteristics of Deep Learning
6 Motivation for Using Deep Learning
7 Machine Learning vs. Deep Learning
8 Challenges of Deep Learning
9 Conclusion and Future Aspects
References
Deep Learning Approaches for Speech Analysis: A Critical Insight
1 Introduction
2 Related Work
3 Proposed Work
4 Results and Discussion
5 Conclusion
References